Identification of patients with congestive heart failure using different neural networks approaches

Nazar Elfadil, Abdulnasir Hossen

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

A new technique for identification of patients with congestive heart failure (CHF) from normal controls is investigated in this paper using spectral analysis and neural networks. The identification system consists of two parts: feature extraction part and classification part. The feature extraction part uses the method of approximate spectral density estimation of R-R-Intervals (RRI) data by implementing the soft decision sub-band decomposition technique. In the classification part, two different methods of machine learning approaches with neural networks are implemented and compared in their performances. Those approaches are: supervised neural network (back-propagation) and unsupervised neural network (Kohonen self organizing maps). The data used in this work is obtained from Massachusetts Institute of Technology (MIT) databases. A data set of 17 CHF and 53 normal subjects is used as original training data set, while another set of 12 CHF and 12 normal subjects is used as original test data set. The classification features are the spectral density of 6 different regions covering the whole spectrum of the RRI data obtained by 32-bands soft decision algorithm. A larger training data set, which is obtained by simulating 1000 CHF and 1000 normal subjects according to the spectral features obtained from the original training data, is used to train the neural network. The neural network is used then to test another simulated data set of the same size of the training date set (simulated according to the spectral features obtained from the original test data set). The accuracy of the classification is found to be about 83.65% and 91.43% with supervised neural networks and unsupervised neural networks respectively.

Original languageEnglish
Pages (from-to)305-321
Number of pages17
JournalTechnology and Health Care
Volume17
Issue number4
DOIs
Publication statusPublished - 2009

Fingerprint

Heart Failure
Neural networks
Spectral density
Feature extraction
Datasets
Self organizing maps
Backpropagation
Databases
Spectrum analysis
Technology
Learning systems
Identification (control systems)
Decomposition

Keywords

  • Back-propagation neural network
  • Congestive Heart Failure (CHF)
  • Kohonen neural network
  • RRI
  • Spectral analysis
  • Subband decomposition

ASJC Scopus subject areas

  • Biophysics
  • Biomaterials
  • Bioengineering
  • Biomedical Engineering
  • Information Systems
  • Health Informatics

Cite this

Identification of patients with congestive heart failure using different neural networks approaches. / Elfadil, Nazar; Hossen, Abdulnasir.

In: Technology and Health Care, Vol. 17, No. 4, 2009, p. 305-321.

Research output: Contribution to journalArticle

@article{0f3c1970c6ae46008d341370e791a660,
title = "Identification of patients with congestive heart failure using different neural networks approaches",
abstract = "A new technique for identification of patients with congestive heart failure (CHF) from normal controls is investigated in this paper using spectral analysis and neural networks. The identification system consists of two parts: feature extraction part and classification part. The feature extraction part uses the method of approximate spectral density estimation of R-R-Intervals (RRI) data by implementing the soft decision sub-band decomposition technique. In the classification part, two different methods of machine learning approaches with neural networks are implemented and compared in their performances. Those approaches are: supervised neural network (back-propagation) and unsupervised neural network (Kohonen self organizing maps). The data used in this work is obtained from Massachusetts Institute of Technology (MIT) databases. A data set of 17 CHF and 53 normal subjects is used as original training data set, while another set of 12 CHF and 12 normal subjects is used as original test data set. The classification features are the spectral density of 6 different regions covering the whole spectrum of the RRI data obtained by 32-bands soft decision algorithm. A larger training data set, which is obtained by simulating 1000 CHF and 1000 normal subjects according to the spectral features obtained from the original training data, is used to train the neural network. The neural network is used then to test another simulated data set of the same size of the training date set (simulated according to the spectral features obtained from the original test data set). The accuracy of the classification is found to be about 83.65{\%} and 91.43{\%} with supervised neural networks and unsupervised neural networks respectively.",
keywords = "Back-propagation neural network, Congestive Heart Failure (CHF), Kohonen neural network, RRI, Spectral analysis, Subband decomposition",
author = "Nazar Elfadil and Abdulnasir Hossen",
year = "2009",
doi = "10.3233/THC-2009-0542",
language = "English",
volume = "17",
pages = "305--321",
journal = "Technology and Health Care",
issn = "0928-7329",
publisher = "IOS Press",
number = "4",

}

TY - JOUR

T1 - Identification of patients with congestive heart failure using different neural networks approaches

AU - Elfadil, Nazar

AU - Hossen, Abdulnasir

PY - 2009

Y1 - 2009

N2 - A new technique for identification of patients with congestive heart failure (CHF) from normal controls is investigated in this paper using spectral analysis and neural networks. The identification system consists of two parts: feature extraction part and classification part. The feature extraction part uses the method of approximate spectral density estimation of R-R-Intervals (RRI) data by implementing the soft decision sub-band decomposition technique. In the classification part, two different methods of machine learning approaches with neural networks are implemented and compared in their performances. Those approaches are: supervised neural network (back-propagation) and unsupervised neural network (Kohonen self organizing maps). The data used in this work is obtained from Massachusetts Institute of Technology (MIT) databases. A data set of 17 CHF and 53 normal subjects is used as original training data set, while another set of 12 CHF and 12 normal subjects is used as original test data set. The classification features are the spectral density of 6 different regions covering the whole spectrum of the RRI data obtained by 32-bands soft decision algorithm. A larger training data set, which is obtained by simulating 1000 CHF and 1000 normal subjects according to the spectral features obtained from the original training data, is used to train the neural network. The neural network is used then to test another simulated data set of the same size of the training date set (simulated according to the spectral features obtained from the original test data set). The accuracy of the classification is found to be about 83.65% and 91.43% with supervised neural networks and unsupervised neural networks respectively.

AB - A new technique for identification of patients with congestive heart failure (CHF) from normal controls is investigated in this paper using spectral analysis and neural networks. The identification system consists of two parts: feature extraction part and classification part. The feature extraction part uses the method of approximate spectral density estimation of R-R-Intervals (RRI) data by implementing the soft decision sub-band decomposition technique. In the classification part, two different methods of machine learning approaches with neural networks are implemented and compared in their performances. Those approaches are: supervised neural network (back-propagation) and unsupervised neural network (Kohonen self organizing maps). The data used in this work is obtained from Massachusetts Institute of Technology (MIT) databases. A data set of 17 CHF and 53 normal subjects is used as original training data set, while another set of 12 CHF and 12 normal subjects is used as original test data set. The classification features are the spectral density of 6 different regions covering the whole spectrum of the RRI data obtained by 32-bands soft decision algorithm. A larger training data set, which is obtained by simulating 1000 CHF and 1000 normal subjects according to the spectral features obtained from the original training data, is used to train the neural network. The neural network is used then to test another simulated data set of the same size of the training date set (simulated according to the spectral features obtained from the original test data set). The accuracy of the classification is found to be about 83.65% and 91.43% with supervised neural networks and unsupervised neural networks respectively.

KW - Back-propagation neural network

KW - Congestive Heart Failure (CHF)

KW - Kohonen neural network

KW - RRI

KW - Spectral analysis

KW - Subband decomposition

UR - http://www.scopus.com/inward/record.url?scp=70350328443&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70350328443&partnerID=8YFLogxK

U2 - 10.3233/THC-2009-0542

DO - 10.3233/THC-2009-0542

M3 - Article

C2 - 19822947

AN - SCOPUS:70350328443

VL - 17

SP - 305

EP - 321

JO - Technology and Health Care

JF - Technology and Health Care

SN - 0928-7329

IS - 4

ER -